8 files changed, 536 insertions, 418 deletions

diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 7cbcaf4f0194..d189c5262bdb 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -232,8 +232,21 @@ config IP_NF_NAT
 
 if IP_NF_NAT
 
+config NF_NAT_MASQUERADE_IPV4
+	tristate "IPv4 masquerade support"
+	help
+	This is the kernel functionality to provide NAT in the masquerade
+	flavour (automatic source address selection).
+
+config NFT_MASQ_IPV4
+	tristate "IPv4 masquerading support for nf_tables"
+	depends on NF_TABLES_IPV4
+	depends on NFT_MASQ
+	select NF_NAT_MASQUERADE_IPV4
+
 config IP_NF_TARGET_MASQUERADE
 	tristate "MASQUERADE target support"
+	select NF_NAT_MASQUERADE_IPV4
 	default m if NETFILTER_ADVANCED=n
 	help
 	  Masquerading is a special case of NAT: all outgoing connections are
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index edf4af32e9f2..14488cc5fd2c 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_NF_LOG_IPV4) += nf_log_ipv4.o
 obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o
 obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o
 obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
+obj-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o
 
 # NAT protocols (nf_nat)
 obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
@@ -35,6 +36,7 @@ obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
 obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
+obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o
 obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o
 
 # generic IP tables 
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index 00352ce0f0de..da7f02a0b868 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -22,6 +22,7 @@
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter/x_tables.h>
 #include <net/netfilter/nf_nat.h>
+#include <net/netfilter/ipv4/nf_nat_masquerade.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
@@ -46,103 +47,17 @@ static int masquerade_tg_check(const struct xt_tgchk_param *par)
 static unsigned int
 masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
-	struct nf_conn *ct;
-	struct nf_conn_nat *nat;
-	enum ip_conntrack_info ctinfo;
-	struct nf_nat_range newrange;
+	struct nf_nat_range range;
 	const struct nf_nat_ipv4_multi_range_compat *mr;
-	const struct rtable *rt;
-	__be32 newsrc, nh;
-
-	NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING);
-
-	ct = nf_ct_get(skb, &ctinfo);
-	nat = nfct_nat(ct);
-
-	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
-			    ctinfo == IP_CT_RELATED_REPLY));
-
-	/* Source address is 0.0.0.0 - locally generated packet that is
-	 * probably not supposed to be masqueraded.
-	 */
-	if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == 0)
-		return NF_ACCEPT;
 
 	mr = par->targinfo;
-	rt = skb_rtable(skb);
-	nh = rt_nexthop(rt, ip_hdr(skb)->daddr);
-	newsrc = inet_select_addr(par->out, nh, RT_SCOPE_UNIVERSE);
-	if (!newsrc) {
-		pr_info("%s ate my IP address\n", par->out->name);
-		return NF_DROP;
-	}
-
-	nat->masq_index = par->out->ifindex;
-
-	/* Transfer from original range. */
-	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
-	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
-	newrange.flags       = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS;
-	newrange.min_addr.ip = newsrc;
-	newrange.max_addr.ip = newsrc;
-	newrange.min_proto   = mr->range[0].min;
-	newrange.max_proto   = mr->range[0].max;
+	range.flags = mr->range[0].flags;
+	range.min_proto = mr->range[0].min;
+	range.max_proto = mr->range[0].max;
 
-	/* Hand modified range to generic setup. */
-	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+	return nf_nat_masquerade_ipv4(skb, par->hooknum, &range, par->out);
 }
 
-static int
-device_cmp(struct nf_conn *i, void *ifindex)
-{
-	const struct nf_conn_nat *nat = nfct_nat(i);
-
-	if (!nat)
-		return 0;
-	if (nf_ct_l3num(i) != NFPROTO_IPV4)
-		return 0;
-	return nat->masq_index == (int)(long)ifindex;
-}
-
-static int masq_device_event(struct notifier_block *this,
-			     unsigned long event,
-			     void *ptr)
-{
-	const struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct net *net = dev_net(dev);
-
-	if (event == NETDEV_DOWN) {
-		/* Device was downed.  Search entire table for
-		   conntracks which were associated with that device,
-		   and forget them. */
-		NF_CT_ASSERT(dev->ifindex != 0);
-
-		nf_ct_iterate_cleanup(net, device_cmp,
-				      (void *)(long)dev->ifindex, 0, 0);
-	}
-
-	return NOTIFY_DONE;
-}
-
-static int masq_inet_event(struct notifier_block *this,
-			   unsigned long event,
-			   void *ptr)
-{
-	struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
-	struct netdev_notifier_info info;
-
-	netdev_notifier_info_init(&info, dev);
-	return masq_device_event(this, event, &info);
-}
-
-static struct notifier_block masq_dev_notifier = {
-	.notifier_call	= masq_device_event,
-};
-
-static struct notifier_block masq_inet_notifier = {
-	.notifier_call	= masq_inet_event,
-};
-
 static struct xt_target masquerade_tg_reg __read_mostly = {
 	.name		= "MASQUERADE",
 	.family		= NFPROTO_IPV4,
@@ -160,12 +75,8 @@ static int __init masquerade_tg_init(void)
 
 	ret = xt_register_target(&masquerade_tg_reg);
 
-	if (ret == 0) {
-		/* Register for device down reports */
-		register_netdevice_notifier(&masq_dev_notifier);
-		/* Register IP address change reports */
-		register_inetaddr_notifier(&masq_inet_notifier);
-	}
+	if (ret == 0)
+		nf_nat_masquerade_ipv4_register_notifier();
 
 	return ret;
 }
@@ -173,8 +84,7 @@ static int __init masquerade_tg_init(void)
 static void __exit masquerade_tg_exit(void)
 {
 	xt_unregister_target(&masquerade_tg_reg);
-	unregister_netdevice_notifier(&masq_dev_notifier);
-	unregister_inetaddr_notifier(&masq_inet_notifier);
+	nf_nat_masquerade_ipv4_unregister_notifier();
 }
 
 module_init(masquerade_tg_init);
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index f1787c04a4dd..6b67d7e9a75d 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -28,222 +28,57 @@ static const struct xt_table nf_nat_ipv4_table = {
 	.af		= NFPROTO_IPV4,
 };
 
-static unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
-{
-	/* Force range to this IP; let proto decide mapping for
-	 * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
-	 */
-	struct nf_nat_range range;
-
-	range.flags = 0;
-	pr_debug("Allocating NULL binding for %p (%pI4)\n", ct,
-		 HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip :
-		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip);
-
-	return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
-}
-
-static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum,
-				     const struct net_device *in,
-				     const struct net_device *out,
-				     struct nf_conn *ct)
+static unsigned int iptable_nat_do_chain(const struct nf_hook_ops *ops,
+					 struct sk_buff *skb,
+					 const struct net_device *in,
+					 const struct net_device *out,
+					 struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
-	unsigned int ret;
 
-	ret = ipt_do_table(skb, hooknum, in, out, net->ipv4.nat_table);
-	if (ret == NF_ACCEPT) {
-		if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
-			ret = alloc_null_binding(ct, hooknum);
-	}
-	return ret;
+	return ipt_do_table(skb, ops->hooknum, in, out, net->ipv4.nat_table);
 }
 
-static unsigned int
-nf_nat_ipv4_fn(const struct nf_hook_ops *ops,
-	       struct sk_buff *skb,
-	       const struct net_device *in,
-	       const struct net_device *out,
-	       int (*okfn)(struct sk_buff *))
+static unsigned int iptable_nat_ipv4_fn(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					int (*okfn)(struct sk_buff *))
 {
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	struct nf_conn_nat *nat;
-	/* maniptype == SRC for postrouting. */
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
-
-	/* We never see fragments: conntrack defrags on pre-routing
-	 * and local-out, and nf_nat_out protects post-routing.
-	 */
-	NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb)));
-
-	ct = nf_ct_get(skb, &ctinfo);
-	/* Can't track?  It's not due to stress, or conntrack would
-	 * have dropped it.  Hence it's the user's responsibilty to
-	 * packet filter it out, or implement conntrack/NAT for that
-	 * protocol. 8) --RR
-	 */
-	if (!ct)
-		return NF_ACCEPT;
-
-	/* Don't try to NAT if this packet is not conntracked */
-	if (nf_ct_is_untracked(ct))
-		return NF_ACCEPT;
-
-	nat = nf_ct_nat_ext_add(ct);
-	if (nat == NULL)
-		return NF_ACCEPT;
-
-	switch (ctinfo) {
-	case IP_CT_RELATED:
-	case IP_CT_RELATED_REPLY:
-		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
-			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
-							   ops->hooknum))
-				return NF_DROP;
-			else
-				return NF_ACCEPT;
-		}
-		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
-	case IP_CT_NEW:
-		/* Seen it before?  This can happen for loopback, retrans,
-		 * or local packets.
-		 */
-		if (!nf_nat_initialized(ct, maniptype)) {
-			unsigned int ret;
-
-			ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct);
-			if (ret != NF_ACCEPT)
-				return ret;
-		} else {
-			pr_debug("Already setup manip %s for ct %p\n",
-				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
-				 ct);
-			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
-				goto oif_changed;
-		}
-		break;
-
-	default:
-		/* ESTABLISHED */
-		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
-			     ctinfo == IP_CT_ESTABLISHED_REPLY);
-		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
-			goto oif_changed;
-	}
-
-	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
-
-oif_changed:
-	nf_ct_kill_acct(ct, ctinfo, skb);
-	return NF_DROP;
+	return nf_nat_ipv4_fn(ops, skb, in, out, iptable_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv4_in(const struct nf_hook_ops *ops,
-	       struct sk_buff *skb,
-	       const struct net_device *in,
-	       const struct net_device *out,
-	       int (*okfn)(struct sk_buff *))
+static unsigned int iptable_nat_ipv4_in(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					int (*okfn)(struct sk_buff *))
 {
-	unsigned int ret;
-	__be32 daddr = ip_hdr(skb)->daddr;
-
-	ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    daddr != ip_hdr(skb)->daddr)
-		skb_dst_drop(skb);
-
-	return ret;
+	return nf_nat_ipv4_in(ops, skb, in, out, iptable_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv4_out(const struct nf_hook_ops *ops,
-		struct sk_buff *skb,
-		const struct net_device *in,
-		const struct net_device *out,
-		int (*okfn)(struct sk_buff *))
+static unsigned int iptable_nat_ipv4_out(const struct nf_hook_ops *ops,
+					 struct sk_buff *skb,
+					 const struct net_device *in,
+					 const struct net_device *out,
+					 int (*okfn)(struct sk_buff *))
 {
-#ifdef CONFIG_XFRM
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	int err;
-#endif
-	unsigned int ret;
-
-	/* root is playing with raw sockets. */
-	if (skb->len < sizeof(struct iphdr) ||
-	    ip_hdrlen(skb) < sizeof(struct iphdr))
-		return NF_ACCEPT;
-
-	ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn);
-#ifdef CONFIG_XFRM
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if ((ct->tuplehash[dir].tuple.src.u3.ip !=
-		     ct->tuplehash[!dir].tuple.dst.u3.ip) ||
-		    (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
-		     ct->tuplehash[dir].tuple.src.u.all !=
-		     ct->tuplehash[!dir].tuple.dst.u.all)) {
-			err = nf_xfrm_me_harder(skb, AF_INET);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-	}
-#endif
-	return ret;
+	return nf_nat_ipv4_out(ops, skb, in, out, iptable_nat_do_chain);
 }
 
-static unsigned int
-nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops,
-		     struct sk_buff *skb,
-		     const struct net_device *in,
-		     const struct net_device *out,
-		     int (*okfn)(struct sk_buff *))
+static unsigned int iptable_nat_ipv4_local_fn(const struct nf_hook_ops *ops,
+					      struct sk_buff *skb,
+					      const struct net_device *in,
+					      const struct net_device *out,
+					      int (*okfn)(struct sk_buff *))
 {
-	const struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	unsigned int ret;
-	int err;
-
-	/* root is playing with raw sockets. */
-	if (skb->len < sizeof(struct iphdr) ||
-	    ip_hdrlen(skb) < sizeof(struct iphdr))
-		return NF_ACCEPT;
-
-	ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
-		    ct->tuplehash[!dir].tuple.src.u3.ip) {
-			err = ip_route_me_harder(skb, RTN_UNSPEC);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-#ifdef CONFIG_XFRM
-		else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
-			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
-			 ct->tuplehash[dir].tuple.dst.u.all !=
-			 ct->tuplehash[!dir].tuple.src.u.all) {
-			err = nf_xfrm_me_harder(skb, AF_INET);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-#endif
-	}
-	return ret;
+	return nf_nat_ipv4_local_fn(ops, skb, in, out, iptable_nat_do_chain);
 }
 
 static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_ipv4_in,
+		.hook		= iptable_nat_ipv4_in,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_PRE_ROUTING,
@@ -251,7 +86,7 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_ipv4_out,
+		.hook		= iptable_nat_ipv4_out,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_POST_ROUTING,
@@ -259,7 +94,7 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	},
 	/* Before packet filtering, change destination */
 	{
-		.hook		= nf_nat_ipv4_local_fn,
+		.hook		= iptable_nat_ipv4_local_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_LOCAL_OUT,
@@ -267,7 +102,7 @@ static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = {
 	},
 	/* After packet filtering, change source */
 	{
-		.hook		= nf_nat_ipv4_fn,
+		.hook		= iptable_nat_ipv4_fn,
 		.owner		= THIS_MODULE,
 		.pf		= NFPROTO_IPV4,
 		.hooknum	= NF_INET_LOCAL_IN,
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index 14f5ccd06337..fc37711e11f3 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -254,6 +254,205 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation);
 
+unsigned int
+nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	       const struct net_device *in, const struct net_device *out,
+	       unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					struct nf_conn *ct))
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn_nat *nat;
+	/* maniptype == SRC for postrouting. */
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
+
+	/* We never see fragments: conntrack defrags on pre-routing
+	 * and local-out, and nf_nat_out protects post-routing.
+	 */
+	NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb)));
+
+	ct = nf_ct_get(skb, &ctinfo);
+	/* Can't track?  It's not due to stress, or conntrack would
+	 * have dropped it.  Hence it's the user's responsibilty to
+	 * packet filter it out, or implement conntrack/NAT for that
+	 * protocol. 8) --RR
+	 */
+	if (!ct)
+		return NF_ACCEPT;
+
+	/* Don't try to NAT if this packet is not conntracked */
+	if (nf_ct_is_untracked(ct))
+		return NF_ACCEPT;
+
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
+
+	switch (ctinfo) {
+	case IP_CT_RELATED:
+	case IP_CT_RELATED_REPLY:
+		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
+			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
+							   ops->hooknum))
+				return NF_DROP;
+			else
+				return NF_ACCEPT;
+		}
+		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
+	case IP_CT_NEW:
+		/* Seen it before?  This can happen for loopback, retrans,
+		 * or local packets.
+		 */
+		if (!nf_nat_initialized(ct, maniptype)) {
+			unsigned int ret;
+
+			ret = do_chain(ops, skb, in, out, ct);
+			if (ret != NF_ACCEPT)
+				return ret;
+
+			if (nf_nat_initialized(ct, HOOK2MANIP(ops->hooknum)))
+				break;
+
+			ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
+			if (ret != NF_ACCEPT)
+				return ret;
+		} else {
+			pr_debug("Already setup manip %s for ct %p\n",
+				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
+				 ct);
+			if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
+				goto oif_changed;
+		}
+		break;
+
+	default:
+		/* ESTABLISHED */
+		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
+			     ctinfo == IP_CT_ESTABLISHED_REPLY);
+		if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out))
+			goto oif_changed;
+	}
+
+	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
+
+oif_changed:
+	nf_ct_kill_acct(ct, ctinfo, skb);
+	return NF_DROP;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv4_fn);
+
+unsigned int
+nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb,
+	       const struct net_device *in, const struct net_device *out,
+	       unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					 struct sk_buff *skb,
+					 const struct net_device *in,
+					 const struct net_device *out,
+					 struct nf_conn *ct))
+{
+	unsigned int ret;
+	__be32 daddr = ip_hdr(skb)->daddr;
+
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    daddr != ip_hdr(skb)->daddr)
+		skb_dst_drop(skb);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv4_in);
+
+unsigned int
+nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb,
+		const struct net_device *in, const struct net_device *out,
+		unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					  struct sk_buff *skb,
+					  const struct net_device *in,
+					  const struct net_device *out,
+					  struct nf_conn *ct))
+{
+#ifdef CONFIG_XFRM
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	int err;
+#endif
+	unsigned int ret;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct iphdr) ||
+	    ip_hdrlen(skb) < sizeof(struct iphdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain);
+#ifdef CONFIG_XFRM
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if ((ct->tuplehash[dir].tuple.src.u3.ip !=
+		     ct->tuplehash[!dir].tuple.dst.u3.ip) ||
+		    (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
+		     ct->tuplehash[dir].tuple.src.u.all !=
+		     ct->tuplehash[!dir].tuple.dst.u.all)) {
+			err = nf_xfrm_me_harder(skb, AF_INET);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+	}
+#endif
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv4_out);
+
+unsigned int
+nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb,
+		     const struct net_device *in, const struct net_device *out,
+		     unsigned int (*do_chain)(const struct nf_hook_ops *ops,
+					       struct sk_buff *skb,
+					       const struct net_device *in,
+					       const struct net_device *out,
+					       struct nf_conn *ct))
+{
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	unsigned int ret;
+	int err;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct iphdr) ||
+	    ip_hdrlen(skb) < sizeof(struct iphdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv4_fn(ops, skb, in, out, do_chain);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
+		    ct->tuplehash[!dir].tuple.src.u3.ip) {
+			err = ip_route_me_harder(skb, RTN_UNSPEC);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+#ifdef CONFIG_XFRM
+		else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
+			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
+			 ct->tuplehash[dir].tuple.dst.u.all !=
+			 ct->tuplehash[!dir].tuple.src.u.all) {
+			err = nf_xfrm_me_harder(skb, AF_INET);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+#endif
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_ipv4_local_fn);
+
 static int __init nf_nat_l3proto_ipv4_init(void)
 {
 	int err;
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
new file mode 100644
index 000000000000..c6eb42100e9a
--- /dev/null
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -0,0 +1,153 @@
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/atomic.h>
+#include <linux/inetdevice.h>
+#include <linux/ip.h>
+#include <linux/timer.h>
+#include <linux/netfilter.h>
+#include <net/protocol.h>
+#include <net/ip.h>
+#include <net/checksum.h>
+#include <net/route.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/ipv4/nf_nat_masquerade.h>
+
+unsigned int
+nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
+		       const struct nf_nat_range *range,
+		       const struct net_device *out)
+{
+	struct nf_conn *ct;
+	struct nf_conn_nat *nat;
+	enum ip_conntrack_info ctinfo;
+	struct nf_nat_range newrange;
+	const struct rtable *rt;
+	__be32 newsrc, nh;
+
+	NF_CT_ASSERT(hooknum == NF_INET_POST_ROUTING);
+
+	ct = nf_ct_get(skb, &ctinfo);
+	nat = nfct_nat(ct);
+
+	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
+			    ctinfo == IP_CT_RELATED_REPLY));
+
+	/* Source address is 0.0.0.0 - locally generated packet that is
+	 * probably not supposed to be masqueraded.
+	 */
+	if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == 0)
+		return NF_ACCEPT;
+
+	rt = skb_rtable(skb);
+	nh = rt_nexthop(rt, ip_hdr(skb)->daddr);
+	newsrc = inet_select_addr(out, nh, RT_SCOPE_UNIVERSE);
+	if (!newsrc) {
+		pr_info("%s ate my IP address\n", out->name);
+		return NF_DROP;
+	}
+
+	nat->masq_index = out->ifindex;
+
+	/* Transfer from original range. */
+	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
+	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
+	newrange.flags       = range->flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.ip = newsrc;
+	newrange.max_addr.ip = newsrc;
+	newrange.min_proto   = range->min_proto;
+	newrange.max_proto   = range->max_proto;
+
+	/* Hand modified range to generic setup. */
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4);
+
+static int device_cmp(struct nf_conn *i, void *ifindex)
+{
+	const struct nf_conn_nat *nat = nfct_nat(i);
+
+	if (!nat)
+		return 0;
+	if (nf_ct_l3num(i) != NFPROTO_IPV4)
+		return 0;
+	return nat->masq_index == (int)(long)ifindex;
+}
+
+static int masq_device_event(struct notifier_block *this,
+			     unsigned long event,
+			     void *ptr)
+{
+	const struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct net *net = dev_net(dev);
+
+	if (event == NETDEV_DOWN) {
+		/* Device was downed.  Search entire table for
+		 * conntracks which were associated with that device,
+		 * and forget them.
+		 */
+		NF_CT_ASSERT(dev->ifindex != 0);
+
+		nf_ct_iterate_cleanup(net, device_cmp,
+				      (void *)(long)dev->ifindex, 0, 0);
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int masq_inet_event(struct notifier_block *this,
+			   unsigned long event,
+			   void *ptr)
+{
+	struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
+	struct netdev_notifier_info info;
+
+	netdev_notifier_info_init(&info, dev);
+	return masq_device_event(this, event, &info);
+}
+
+static struct notifier_block masq_dev_notifier = {
+	.notifier_call	= masq_device_event,
+};
+
+static struct notifier_block masq_inet_notifier = {
+	.notifier_call	= masq_inet_event,
+};
+
+static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+
+void nf_nat_masquerade_ipv4_register_notifier(void)
+{
+	/* check if the notifier was already set */
+	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
+		return;
+
+	/* Register for device down reports */
+	register_netdevice_notifier(&masq_dev_notifier);
+	/* Register IP address change reports */
+	register_inetaddr_notifier(&masq_inet_notifier);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier);
+
+void nf_nat_masquerade_ipv4_unregister_notifier(void)
+{
+	/* check if the notifier still has clients */
+	if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
+		return;
+
+	unregister_netdevice_notifier(&masq_dev_notifier);
+	unregister_inetaddr_notifier(&masq_inet_notifier);
+}
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>");
diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
index 3964157d826c..df547bf50078 100644
--- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
@@ -26,136 +26,53 @@
 #include <net/netfilter/nf_nat_l3proto.h>
 #include <net/ip.h>
 
-/*
- * NAT chains
- */
-
-static unsigned int nf_nat_fn(const struct nf_hook_ops *ops,
-			      struct sk_buff *skb,
-			      const struct net_device *in,
-			      const struct net_device *out,
-			      int (*okfn)(struct sk_buff *))
+static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops,
+				      struct sk_buff *skb,
+				      const struct net_device *in,
+				      const struct net_device *out,
+				      struct nf_conn *ct)
 {
-	enum ip_conntrack_info ctinfo;
-	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
-	struct nf_conn_nat *nat;
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum);
 	struct nft_pktinfo pkt;
-	unsigned int ret;
-
-	if (ct == NULL || nf_ct_is_untracked(ct))
-		return NF_ACCEPT;
-
-	NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)));
-
-	nat = nf_ct_nat_ext_add(ct);
-	if (nat == NULL)
-		return NF_ACCEPT;
-
-	switch (ctinfo) {
-	case IP_CT_RELATED:
-	case IP_CT_RELATED + IP_CT_IS_REPLY:
-		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
-			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
-							   ops->hooknum))
-				return NF_DROP;
-			else
-				return NF_ACCEPT;
-		}
-		/* Fall through */
-	case IP_CT_NEW:
-		if (nf_nat_initialized(ct, maniptype))
-			break;
 
-		nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out);
+	nft_set_pktinfo_ipv4(&pkt, ops, skb, in, out);
 
-		ret = nft_do_chain(&pkt, ops);
-		if (ret != NF_ACCEPT)
-			return ret;
-		if (!nf_nat_initialized(ct, maniptype)) {
-			ret = nf_nat_alloc_null_binding(ct, ops->hooknum);
-			if (ret != NF_ACCEPT)
-				return ret;
-		}
-	default:
-		break;
-	}
-
-	return nf_nat_packet(ct, ctinfo, ops->hooknum, skb);
+	return nft_do_chain(&pkt, ops);
 }
 
-static unsigned int nf_nat_prerouting(const struct nf_hook_ops *ops,
-				      struct sk_buff *skb,
-				      const struct net_device *in,
-				      const struct net_device *out,
-				      int (*okfn)(struct sk_buff *))
+static unsigned int nft_nat_ipv4_fn(const struct nf_hook_ops *ops,
+				    struct sk_buff *skb,
+				    const struct net_device *in,
+				    const struct net_device *out,
+				    int (*okfn)(struct sk_buff *))
 {
-	__be32 daddr = ip_hdr(skb)->daddr;
-	unsigned int ret;
-
-	ret = nf_nat_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    ip_hdr(skb)->daddr != daddr) {
-		skb_dst_drop(skb);
-	}
-	return ret;
+	return nf_nat_ipv4_fn(ops, skb, in, out, nft_nat_do_chain);
 }
 
-static unsigned int nf_nat_postrouting(const struct nf_hook_ops *ops,
-				       struct sk_buff *skb,
-				       const struct net_device *in,
-				       const struct net_device *out,
-				       int (*okfn)(struct sk_buff *))
+static unsigned int nft_nat_ipv4_in(const struct nf_hook_ops *ops,
+				    struct sk_buff *skb,
+				    const struct net_device *in,
+				    const struct net_device *out,
+				    int (*okfn)(struct sk_buff *))
 {
-	enum ip_conntrack_info ctinfo __maybe_unused;
-	const struct nf_conn *ct __maybe_unused;
-	unsigned int ret;
-
-	ret = nf_nat_fn(ops, skb, in, out, okfn);
-#ifdef CONFIG_XFRM
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-
-		if (ct->tuplehash[dir].tuple.src.u3.ip !=
-		    ct->tuplehash[!dir].tuple.dst.u3.ip ||
-		    ct->tuplehash[dir].tuple.src.u.all !=
-		    ct->tuplehash[!dir].tuple.dst.u.all)
-			return nf_xfrm_me_harder(skb, AF_INET) == 0 ?
-								ret : NF_DROP;
-	}
-#endif
-	return ret;
+	return nf_nat_ipv4_in(ops, skb, in, out, nft_nat_do_chain);
 }
 
-static unsigned int nf_nat_output(const struct nf_hook_ops *ops,
-				  struct sk_buff *skb,
-				  const struct net_device *in,
-				  const struct net_device *out,
-				  int (*okfn)(struct sk_buff *))
+static unsigned int nft_nat_ipv4_out(const struct nf_hook_ops *ops,
+				     struct sk_buff *skb,
+				     const struct net_device *in,
+				     const struct net_device *out,
+				     int (*okfn)(struct sk_buff *))
 {
-	enum ip_conntrack_info ctinfo;
-	const struct nf_conn *ct;
-	unsigned int ret;
-
-	ret = nf_nat_fn(ops, skb, in, out, okfn);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
-		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+	return nf_nat_ipv4_out(ops, skb, in, out, nft_nat_do_chain);
+}
 
-		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
-		    ct->tuplehash[!dir].tuple.src.u3.ip) {
-			if (ip_route_me_harder(skb, RTN_UNSPEC))
-				ret = NF_DROP;
-		}
-#ifdef CONFIG_XFRM
-		else if (ct->tuplehash[dir].tuple.dst.u.all !=
-			 ct->tuplehash[!dir].tuple.src.u.all)
-			if (nf_xfrm_me_harder(skb, AF_INET))
-				ret = NF_DROP;
-#endif
-	}
-	return ret;
+static unsigned int nft_nat_ipv4_local_fn(const struct nf_hook_ops *ops,
+					  struct sk_buff *skb,
+					  const struct net_device *in,
+					  const struct net_device *out,
+					  int (*okfn)(struct sk_buff *))
+{
+	return nf_nat_ipv4_local_fn(ops, skb, in, out, nft_nat_do_chain);
 }
 
 static const struct nf_chain_type nft_chain_nat_ipv4 = {
@@ -168,10 +85,10 @@ static const struct nf_chain_type nft_chain_nat_ipv4 = {
 			  (1 << NF_INET_LOCAL_OUT) |
 			  (1 << NF_INET_LOCAL_IN),
 	.hooks		= {
-		[NF_INET_PRE_ROUTING]	= nf_nat_prerouting,
-		[NF_INET_POST_ROUTING]	= nf_nat_postrouting,
-		[NF_INET_LOCAL_OUT]	= nf_nat_output,
-		[NF_INET_LOCAL_IN]	= nf_nat_fn,
+		[NF_INET_PRE_ROUTING]	= nft_nat_ipv4_in,
+		[NF_INET_POST_ROUTING]	= nft_nat_ipv4_out,
+		[NF_INET_LOCAL_OUT]	= nft_nat_ipv4_local_fn,
+		[NF_INET_LOCAL_IN]	= nft_nat_ipv4_fn,
 	},
 };
 
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
new file mode 100644
index 000000000000..6ea1d207b6a5
--- /dev/null
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -0,0 +1,89 @@
+/*
+ * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_masq.h>
+#include <net/netfilter/ipv4/nf_nat_masquerade.h>
+
+static void nft_masq_ipv4_eval(const struct nft_expr *expr,
+			       struct nft_data data[NFT_REG_MAX + 1],
+			       const struct nft_pktinfo *pkt)
+{
+	struct nft_masq *priv = nft_expr_priv(expr);
+	struct nf_nat_range range;
+	unsigned int verdict;
+
+	range.flags = priv->flags;
+
+	verdict = nf_nat_masquerade_ipv4(pkt->skb, pkt->ops->hooknum,
+					 &range, pkt->out);
+
+	data[NFT_REG_VERDICT].verdict = verdict;
+}
+
+static int nft_masq_ipv4_init(const struct nft_ctx *ctx,
+			      const struct nft_expr *expr,
+			      const struct nlattr * const tb[])
+{
+	int err;
+
+	err = nft_masq_init(ctx, expr, tb);
+	if (err < 0)
+		return err;
+
+	nf_nat_masquerade_ipv4_register_notifier();
+	return 0;
+}
+
+static void nft_masq_ipv4_destroy(const struct nft_ctx *ctx,
+				  const struct nft_expr *expr)
+{
+	nf_nat_masquerade_ipv4_unregister_notifier();
+}
+
+static struct nft_expr_type nft_masq_ipv4_type;
+static const struct nft_expr_ops nft_masq_ipv4_ops = {
+	.type		= &nft_masq_ipv4_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
+	.eval		= nft_masq_ipv4_eval,
+	.init		= nft_masq_ipv4_init,
+	.destroy	= nft_masq_ipv4_destroy,
+	.dump		= nft_masq_dump,
+};
+
+static struct nft_expr_type nft_masq_ipv4_type __read_mostly = {
+	.family		= NFPROTO_IPV4,
+	.name		= "masq",
+	.ops		= &nft_masq_ipv4_ops,
+	.policy		= nft_masq_policy,
+	.maxattr	= NFTA_MASQ_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_masq_ipv4_module_init(void)
+{
+	return nft_register_expr(&nft_masq_ipv4_type);
+}
+
+static void __exit nft_masq_ipv4_module_exit(void)
+{
+	nft_unregister_expr(&nft_masq_ipv4_type);
+}
+
+module_init(nft_masq_ipv4_module_init);
+module_exit(nft_masq_ipv4_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "masq");